US 12,340,967 B2
Methods, mediums, and systems for identifying tunable domains for ion beam shape matching
Richard Allen Sprenkle, South Hamilton, MA (US); Richard White, Newmarket, NH (US); Eric Donald Wilson, Rockport, MA (US); Shane Conley, Gloucester, MA (US); Ana Samolov, Somerville, MA (US); and Nilay A. Pradhan, Santa Clara, CA (US)
Assigned to Applied Materials, Inc., Santa Clara, CA (US)
Filed by Applied Materials, Inc., Santa Clara, CA (US)
Filed on Jul. 14, 2021, as Appl. No. 17/375,488.
Prior Publication US 2023/0013095 A1, Jan. 19, 2023
Int. Cl. H01J 3/12 (2006.01); G05B 19/4155 (2006.01); G06N 20/00 (2019.01)
CPC H01J 3/12 (2013.01) [G05B 19/4155 (2013.01); G06N 20/00 (2019.01); G05B 2219/36199 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving one or more desired beam shape parameters for an ion beam and one or more tunable parameters for an ion beam generator configured to generate the ion beam;
selecting a set of exploratory points within a search space, each point in the search space representing a combination of values for the tunable parameters;
for each of the exploratory points, receiving measured beam shape parameters based on the combination of values for the tunable parameters defined by the respective exploratory point;
training a regression model configured to provide predicted beam shape parameters for a predetermined number of interpolated points between spaced around the exploratory points;
defining a plurality of clusters within the search space based on the predicted beam shape parameters and the measured beam shape parameters;
evaluating the plurality of clusters for at least one of a stability or a sensitivity of the tunable parameters within each respective cluster;
selecting one of the plurality of clusters based on the evaluating; and
outputting tuning settings for the combination of values for the tunable parameters corresponding to the selected cluster.